RAG、ベクターデータベース、MCPをつないで考えたこと
https://papoo.work/doc/9ac64960fa4f374c
#rag #ベクターデータベース #mcp #ai #検索システム

🔎 all-MiniLM-L6-v2 quietly powers most enterprise semantic search and RAG stacks. 384 dim vectors, 90 MB, CPU friendly, Apache 2.0. Full guide: architecture, chunking, hybrid retrieval, reranking. aiadoptionagency.com/all-minilm-l... #SemanticSearch #RAG

Netanyahu says pilot arrested after stabbing another pilot and apparently trying to crash Israel-bound plane
www.bbc.co.uk/news/live/cw...

#violent #violence #inbreeding
#headcase #rag #head #nutters #sameolesameole
#boring

Perplexity baut Retrieval selbst: Photon, in Rust, drückt die p99-Latenz von 800 ms auf 65 ms. Bei Agenten ist Suche der Flaschenhals – das ist der eigentliche Hebel. #RAG

Mehr von mir: linkedin.com/in/maurice-putinas

New research introduces AdaTutoRank, optimizing document set reranking via Adaptive Tutoring Optimization for advanced RAG.
Evidence: Setwise reranking, Hierarchical rubrics, Reduced retrieval calls
#AI #RAG #Research 🌐

Un #LLM puede recuperar el documento equivocado o usar mal una herramienta y, aun así, redactar algo convincente.

Por eso conviene evaluar cada etapa (recuperación en #RAG, herramientas, traspasos entre agentes) y el flujo completo: ¿se resolvió la tarea de principio a fin?

GenePattern Copilot, an #AgenticAI #RAG assistant, initially hallucinated modules.

To fix this, we added a tool to fetch the real module list. This evolved into an #MCP server wrapping the GenePattern REST API, turning the Q&A bot into a full agent that could launch jobs and retrieve results.​

The part of this article I’d actually trust
https://papoo.work/doc/addd14a6d00210db
#claudenews #rag #vectordatabases #mcp

The part of this article I’d actually trust
https://papoo.work/doc/addd14a6d00210db
#claudenews #rag #vectordatabases #mcp

ARCagent introduces a retrieval-calibrated clinical QA system for ME/CFS that uses a structured inter-guideline conflict registry and conflict-aware re-ranking to surface contested evidence, plus an LLM-as-Judge benchmark. The…

#AI #HealthcareAI #RAG #ClinicalQA
https://arxiv.org/abs/2609.36392

The part of this article I’d actually trust
https://papoo.work/doc/addd14a6d00210db
#claudenews #rag #vectordatabases #mcp

"Building a RAG Application with Amazon Bedrock Knowledge Bases" by Chikkudu Nithin

#ai-agents #agentic-ai #rag #amazon-bedrock #retreival-augmented-generation

The part of this article I’d actually trust
https://papoo.work/doc/addd14a6d00210db
#claudenews #rag #vectordatabases #mcp

"¿Qué sabe realmente un LLM cuando le hacemos una pregunta?" by JuanPi

#rag #generative-ai #amazon-bedrock #llm #machine-learning

RAG is still a practical way to connect #LLMs with enterprise information. But production #RAG is not simply a vector database sitting behind a prompt.
#GenAI #GenerativeAI #data #programming #development

https://bit.ly/4rymvxx

社内の業務マニュアルを探すのに時間をかけていたり、同僚に聞いて迷惑かけていませんか？
社内に安全に立てたAIシステムへ、マニュアルやPDF、Webサイトを登録すれば、AIアバターが即答してくれるんですよ♪
頼れる相棒の詳細はプロフノリンクから！ #AIアシスタント #RAG

The part of this article I’d actually trust
https://papoo.work/doc/addd14a6d00210db
#claudenews #rag #vectordatabases #mcp

The part of this article I’d actually trust
https://papoo.work/doc/addd14a6d00210db
#claudenews #rag #vectordatabases #mcp

Scale enterprise RAG with web crawling! 🕸️

Apache StormCrawler is now native in OpenCrawling:
• StormCrawler 3.7 & Storm 3.1
• Dual-stream UPSERT & DELETE tombstones
• Java 25 Virtual Threads

Read more: opencrawling.org/blog/introdu...

#AI #RAG